
genotype = "AG"
phenotype = "expressed"
if genotype == "AG":
    # Only check phenotype if genotype is "AG"
    if phenotype == "expressed":
        print("Variant is active and expressed.")
    else:
        print("Variant is inactive.")
else:
    print("Non-target variant.")

python yourscript.py

file = open("filename.txt", "r")
content = file.read()
file.close()

file = open("filename.txt", "r")
content = file.read()
file.close()

with open("filename.txt", "r") as file:
    content = file.read()

with open ("filename.txt", "r", encoding='utf-8') as file
    content = file.read()


seqfile = "../files/one_dna_sequence.fa"

with open(seqfile, "r") as file:
    for line in file:
        print(line.strip())


string1  = '  an example string with whitespaces at both ends   '
string2 = string1.strip()
string2


list1 = string2.split()
list1


list2 = string1.strip().split()
list2

file = open("output.txt", "w")
file.write("Hello, Python!")
file.close()


with open("../newproject/output.txt", "w") as file:
    file.write("Hello, Python!")


seqfile = "../files/one_dna_sequence.fa"

with open(seqfile, "r") as file:
    seqlength = 0
    for line in file:
        line = line.strip()
        if not line.startswith(">"):
            seqlength += len(line)

outfile = "../newproject/length_of_dna_sequence.txt"
with open(outfile, "w") as file:
    file.write("Length of DNA sequence: " + str(seqlength))


vcf_file = '../downloads/genotypes_small.vcf'
with open(vcf_file, 'r') as fh:
    for line in fh:
        if not line.startswith('#'):
            line = line.strip()
            print(line)
            break
# Next, find chromosome 5


vcf_file = '../downloads/genotypes_small.vcf'
with open(vcf_file, 'r') as fh:
    for line in fh:
        if not line.startswith('#'):
            line = line.strip()
            cols = line.split('\t')
            chrom = cols[0]
            if chrom == '5':
                print(cols)
                break

# Next, find the correct region


vcf_file = '../downloads/genotypes_small.vcf'
with open(vcf_file, 'r') as fh:
    for line in fh:
        if not line.startswith('#'):
            line = line.strip()
            cols = line.split('\t')
            chrom = cols[0]
            pos = int(cols[1])
            if chrom == '5' and (1200000 <= pos <= 1300000):
                print(cols)
                break
# Next, find the genotypes for sample1


vcf_file = '../downloads/genotypes_small.vcf'
with open(vcf_file, 'r') as fh:
    for line in fh:
        if not line.startswith('#'):
            line = line.strip()
            cols = line.split('\t')
            chrom = cols[0]
            pos = int(cols[1])
            if chrom == '5' and (1200000 <= pos <= 1300000):
                geno_col = cols[9]
                print(geno_col)
                break
                    
# Next, extract the genotypes only


vcf_file = '../downloads/genotypes_small.vcf'
with open(vcf_file, 'r') as fh:
    for line in fh:
        if not line.startswith('#'):
            line = line.strip()
            cols = line.split('\t')
            chrom = cols[0]
            pos = int(cols[1])
            if chrom == '5' and (1200000 <= pos <= 1300000):
                geno_col = cols[9]
                geno = geno_col.split(':')[0]
                print(geno)
                break
                
# Next, find in which positions sample1 has alternate alleles


vcf_file = '../downloads/genotypes_small.vcf'
with open(vcf_file, 'r') as fh:
    for line in fh:
        if not line.startswith('#'):
            line = line.strip()
            cols = line.split('\t')
            chrom = cols[0]
            pos = int(cols[1])
            if chrom == '5' and (1200000 <= pos <= 1300000):
                geno_col = cols[9]
                geno = geno_col.split(':')[0]
                if geno not in ["0/0"]:
                    print(geno)
#Next, print nicely


vcf_file = '../downloads/genotypes_small.vcf'
with open(vcf_file, 'r') as fh:
    for line in fh:
        if not line.startswith('#'):
            line = line.strip()
            cols = line.split('\t')
            chrom = cols[0]
            pos = int(cols[1])
            if chrom == '5' and (1200000 <= pos <= 1300000):
                geno_col = cols[9]
                geno = geno_col.split(':')[0]
                if geno not in ["0/0"]:
                    ref = cols[3]
                    alt = cols[4]
                    info = chrom + ":" + str(pos) + "_" + ref + "-" + alt + " has genotype: "+ geno
                    print(info)

Introduction to Python with Application in Bioinformatics¶

Nanjiang Shu¶

2024-07-16 (Day 2)¶

Review of Day 1¶

Review of the quiz from yesterday¶

Questions?¶

Day 2¶

Session 1: Python script, File I/O¶

Python script¶

Now we will save the code in a text file and try to run it in the terminal¶

About the file extension .py¶

5 mins exercise¶

File I/O - read and write files¶

Read from file¶

Use the with keyword to ensure the file handle be closed automatically¶

You may also specify encoding='utf-8' when opening a file in Python to ensure proper handling of text files that contain non-ASCII characters, such as Chinese characters.¶

However, for Python 3, the default encoding is usually 'utf-8', so it's not needed.¶

Detour: useful methods for string¶

Write to file¶

Similar to file reading, you can also use the with keyword¶

Day 2, Exercise 1¶

Take a break after the exercise¶

Session 2: Variants identification with VCF¶

Description of the task¶

What is your input?¶

Genotype field¶

Start with pseudocode!¶

Task:¶

Open the file and loop over lines (ignore lines starting with #), and print the first record¶

Identify lines where chromosome is 5¶

Identify lines where chromosome is 5 and position is between 1,200,000 and 1,300,000¶

Isolate the column that contains the genotype for sample1¶

Extract only the genotypes from the column¶

Check if the genotype contains any alternate alleles¶

Print any variants containing alternate alleles for this sample between specified region¶

Day 2, Exercise 2¶

Lunch¶

Afternoon session¶

1. Quiz for Day 2¶

2. Introduction to the course project¶

Break¶

3. Team building¶

Introduction to the course project¶

Background¶

Cystic fibrosis (CF)

Genomic facts of Cystic Fibrosis¶

More about the CFTR gene¶

Goal of the project¶

Write a python program that:¶

Data¶

Fasta format¶

GTF format¶

Attributes¶

Project page¶

About the file extension `.py`¶

Use the `with` keyword to ensure the file handle be closed automatically¶

You may also specify `encoding='utf-8'` when opening a file in Python to ensure proper handling of text files that contain non-ASCII characters, such as Chinese characters.¶

Detour: useful methods for `string`¶

Similar to file reading, you can also use the `with` keyword¶

Open the file and loop over lines (ignore lines starting with `#`), and print the first record¶

Identify lines where chromosome is `5`¶

Identify lines where chromosome is `5` and position is between `1,200,000` and `1,300,000`¶